Advanced search
Start date
Betweenand

ALIS: Autonomous Learning in Intelligent System

Abstract

Intelligent systems are machines that have their own goals, perceive, respond and learn based on their experiences. Reinforcement Learning (RL) is a powerful tool for this purpose because the system autonomously learns a policy, through trial and error in repeated interactions with the environment. This project seeks to increase the dissemination of the RL technology and advance the frontiers of knowledge of the self-learning area. However, many challenges must still be overcome in order to have a broad use of RL in intelligent systems. Challenges include dealing with uncertainties of sensors and actuators, a dynamic world that changes continuously and requires quick decisions, continuous quantities and the high RL computational cost. Therefore, this scientific research project aims toinvestigate, propose, develop, and evaluate models and methods to make efficient and effective RL in intelligent systems that solve complex problems. In particular, it explores: (I) relational and object-oriented models and algorithms, opening opportunities for generalization in the representation and solution of complex problems; (Ii) distribution and division of workload among several apprentices agents; (Iii) appropriate approximation functions to represent both situations observed by the agent and the knowledge acquired; (Iv) knowledge transfer so that the knowledge acquired byanother agent or after the learning of previous tasks can be reused to accelerate the learning of a new similar task. From the point of view of applications, this project aims to implement and evaluate models and algorithms in areas such as games, robotics, computational biology, among others. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications (9)
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
DOS SANTOS, THIAGO FREITAS; SANTOS, PAULO E.; FERREIRA, LEONARDO ANJOLETTO; BIANCHI, REINALDO A. C.; CABALAR, PEDRO. euristics, Answer Set Programming and Markov Decision Process for Solving a Set of Spatial Puzzles{*. APPLIED INTELLIGENCE, v. 52, n. 4, . (16/21047-3, 17/07833-9, 16/18792-9)
PERICO, DANILO H.; HOMEM, THIAGO P. D.; ALMEIDA, AISLAN C.; SILVA, ISAAC J.; VILAO, JR., CLAUDIO O.; FERREIRA, VINICIUS N.; BIANCHI, REINALDO A. C.. Humanoid Robot Framework for Research on Cognitive Robotics. JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS, v. 29, n. 4, p. 470-479, . (16/21047-3, 16/18792-9)
DA SILVA, FELIPE LENO; REALI COSTA, ANNA HELENA. A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, v. 64, p. 645-703, . (16/21047-3, 18/00344-5, 15/16310-4)
FERREIRA, LEONARDO A.; BIANCHI, REINALDO A. C.; SANTOS, PAULO E.; LOPEZ DE MANTARAS, RAMON. Answer set programming for non-stationary Markov decision processes. APPLIED INTELLIGENCE, v. 47, n. 4, p. 993-1007, . (11/19280-8, 16/18792-9, 16/21047-3)
GLATT, RUBEN; DA SILVA, FELIPE LENO; DA COSTA BIANCHI, REINALDO AUGUSTO; REALI COSTA, ANNA HELENA. DECAF: Deep Case-based Policy Inference for knowledge transfer in Reinforcement Learning. EXPERT SYSTEMS WITH APPLICATIONS, v. 156, . (16/21047-3, 15/16310-4, 18/00344-5, 16/18792-9)
JACOMINI, RICARDO DE SOUZA; MARTINS, JR., DAVID CORREA; DA SILVA, FELIPE LENO; REALI COSTA, ANNA HELENA. GeNICE: A Novel Framework for Gene Network Inference by Clustering, Exhaustive Search, and Multivariate Analysis. JOURNAL OF COMPUTATIONAL BIOLOGY, v. 24, n. 8, p. 809-830, . (16/21047-3, 11/50761-2, 15/16310-4, 15/01587-0)
BIANCHI, REINALDO A. C.; SANTOS, PAULO E.; DA SILVA, ISAAC J.; CELIBERTO, JR., LUIZ A.; DE MANTARAS, RAMON LOPEZ. Heuristically Accelerated Reinforcement Learning by Means of Case-Based Reasoning and Transfer Learning. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, v. 91, n. 2, SI, p. 301-312, . (16/18792-9, 16/21047-3)
PERAFAN VILLOTA, JUAN CARLOS; DA SILVA, FELIPE LENO; JACOMINI, RICARDO DE SOUZA; REALI COSTA, ANNA HELENA. Pairwise registration in indoor environments using adaptive combination of 2D and 3D cues. Image and Vision Computing, v. 69, p. 113-124, . (16/21047-3, 15/16310-4)
DA SILVA, FELIPE LENO; GLATT, RUBEN; REALI COSTA, ANNA HELENA. MOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning. IEEE TRANSACTIONS ON CYBERNETICS, v. 49, n. 2, p. 567-579, . (16/21047-3, 15/16310-4)

Please report errors in scientific publications list by writing to: cdi@fapesp.br.